In this paper we investigate the behaviour of a peerto peer driven Grid computing network. In contrast to earlier work we limit the budget of the nodes and observe the consequences for the price development. We present mean field approximation of the simulation model and show that it captures the essence of the model. We also show that the proposed peer to peer network scales much better than a central server approach. By allowing the agents in the simulation to hibernate and change the price individually only using local information the price development of the model becomes stable. Lastly we investigate the distribution of the times the agents wait to sell or buy resources.
Information from pubs.doc.ic.ac.uk/grid-epew-2009.